N-MNIST
PulseAugur coverage of N-MNIST — every cluster mentioning N-MNIST across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New Spiking Neural Network Architecture Enhances Image and Event Stream Processing · 3 sources tracked
Researchers have developed a novel spiking neural network (SNN) architecture called Multi-Depth Temporal Fusion (MDTF) designed for processing static images and event streams using time-to-first-spike latencies. This ne…
-
New ANTShapes Datasets Advance Event-Based Neuromorphic Object Classification
Researchers have introduced ANTShapes, a simulation tool designed to generate and label event-based vision datasets for object classification. This paper presents four new datasets created with ANTShapes, which are then…
-
New Bit-Serial CNN Accelerator Boosts XR Vision Efficiency
Researchers have developed BitFair, a novel bit-serial CNN accelerator designed for ultra-low-power Extended Reality (XR) applications. This accelerator incorporates learnable early termination and adaptive bit ordering…
-
New open-source framework aids SNN hardware design and exploration
A new open-source framework has been developed to aid in the design and exploration of mixed-signal spiking neural networks (SNNs) for energy-efficient neuromorphic computing. This framework, built within PyTorch, allow…
-
New open-source framework aids SNN hardware design exploration
Researchers have developed an open-source framework designed to simulate and explore the design space of mixed-signal Spiking Neural Networks (SNNs). This tool integrates device-level nonlinearities directly into PyTorc…
-
New method trains energy-efficient spiking neural networks faster
Researchers have developed EGGROLL, a novel gradient-free method for training Spiking Neural Networks (SNNs) that significantly reduces computational cost. This approach uses low-rank factorization of Evolution Strategi…
-
Liquid Neural Networks Outperform LSTMs in Robustness and Efficiency
A new research paper compares Liquid Neural Networks (LNNs) with traditional Long Short-Term Memory (LSTM) networks for sequential pattern recognition. The study found that LNNs, particularly CfC networks, offer better …